yolo nas pose F.conv2d(input, weight, bias, self.stride, RuntimeError: expected scalar type Byte but found Float about super-gradients HOT 3 CLOSED

Greetings.
Usually this error message indicates that you are sending a uint8 type input to the model and not floats. Which may indicate that you don't have any image normalization. And indeed based on your code you are not using any transformations in training/validation datasets. You will get poor results.

Please follow your tutorial notebook on fine-tuning the YoloNAS-Pose: https://github.com/Deci-AI/super-gradients/blob/master/notebooks/YoloNAS_Pose_Fine_Tuning_Animals_Pose_Dataset.ipynb

from super-gradients.

thank you, will update with results.

Normalize in this context means turning pixel coordinates into floats proportional to the image?

from super-gradients.

Thank you, I was missing the normalization transform from the example. appreciate the prompt response sir!

from super-gradients.